4 Langfuse Jobs

Tech stack required: Programming languages: Python Public Cloud: AzureFrameworks: Vector Databases such as Milvus, Qdrant/ ChromaDB, or usage of CosmosDB or MongoDB as Vector stores. Knowledge of AI Orchestration, AI evaluation and Observability Tools. Knowledge of Guardrails strategy for LLM. Knowledge on Arize or any other ML/LLM observability tool. Experience: Experience in building functional platforms using ML, CV, LLM platforms. Experience in evaluating and monitoring AI platforms in production Nice to have requirements to the candidate Excellent communication skills, both written and verbal. Strong problem-solving and critical-thinking abilities. Effective leadership and mentoring skills. Ability to collaborate with cross-functional teams and stakeholders. Strong attention to detail and a commitment to delivering high-quality solutions. Adaptability and willingness to learn new technologies. Time management and organizational skills to handle multiple projects and priorities.

Senior Software Engineer/ LLM Ops Engineer External Description Description - External JD - What You Will Do Design, implement, and maintain LLM operations workflows using tools like Langfuse to monitor performance, track usage, and create feedback loops for continuous improvement Develop and maintain infrastructure-as-code for AI deployments using Terraform and AWS services (Lambda, SQS, API Gateway, OpenSearch, CloudWatch) Build and enhance monitoring, logging, and alerting systems to ensure optimal performance and reliability of our LLM infrastructure Collaborate with AI engineers to design and implement evaluation frameworks (including LLM-as-judge systems) to measure and improve model performance Manage prompt versioning, testing, and deployment pipelines through CI/CD and custom tooling Implement and maintain security guardrails for LLM interactions, ensuring compliance with best practices Create comprehensive documentation for LLM operations, including runbooks for production incidents Participate in on-call rotations to support mission-critical AI systems Drive innovation in LLM operations by researching and implementing best practices and emerging tools in the rapidly evolving GenAI space Deep understanding of prompt engineering strategies What You Will Bring To succeed in this role, you will need a combination of experience, technology skills, personal qualities, and education. Required Qualifications 3+ years of experience in DevOps, SRE, or similar roles, with at least 1 year specifically working with LLMs or AI systems in production Strong hands-on experience with AWS cloud services, particularly Bedrock, Lambda, SQS, API Gateway, OpenSearch, and CloudWatch Experience with infrastructure-as-code using Terraform, CloudFormation, or similar tools Proficiency in Python and experience building automation tooling and pipelines Familiarity with LangOps platforms such as Langfuse for LLM observability and evaluation Experience with CI/CD pipelines Knowledge of logging, monitoring, and alerting systems Understanding of security best practices for AI systems, including prompt injection mitigation techniques Excellent troubleshooting and problem-solving skills Strong communication skills and ability to work effectively with cross-functional teams Must be legally entitled to work in the country where the role is located Preferred Qualifications Experience with prompt engineering and testing tools like Promptfoo Familiarity with vector databases and retrieval-augmented generation (RAG) systems Knowledge of serverless architectures and event-driven systems Experience with AWS Guardrails for LLM security Background in data engineering or machine learning operations Understanding of financial systems and data security requirements in the finance industry Familiarity with implementing technical solutions to meet compliance requirements outlined in SOC2, ISAE 3402, and ISO 27001

Project Description: Grid Dynamics aims building enterprise generative AI framework to deliver innovative, scalable and efficient AI-driven solutions across business functions.Due to constant scaling of digital capabilities the platform requires enhancements to incorporate cutting-edge generative AI features and meet emerging business demands. Platform should onboard brand new capabilities like Similarity Search (image,video and voice);Ontology and entity managment;voice and file mgmt [text to speech & vice-versa, metadata tagging, multi-media file support];Advanced RAG ; Multi-Modal capabilities Responsibilities: As an LLMOps Engineer, you will be responsible for providing expertise on overseeing the complete lifecycle management of large language models (LLM). This includes the development of strategies for deployment, continuous integration and delivery (CI/CD) processes, performance tuning, and ensuring high availability of our LLM services. You will collaborate closely with data scientists, AI/ML engineers, and IT teams to define and align LLM operations with business goals, ensuring a seamless and efficient operating model. In this role, you will: Define and disseminate LLMOps best practices. Evaluate and compare different LLMOps tools to incorporate the best practices. Stay updated on industry trends and advancements in LLM technologies and operational methodologies. Participate in architecture design/validation sessions for the Generative AI use cases with entities. Contribute to the development and expansion of GenAI use cases, including standard processes, framework, templates, libraries, and best practices around GenAI. Design, implement, and oversee the infrastructure required for the efficient operation of large language models in collaboration with client entities. Provide expertise and guidance to client entities in the development and scaling of GenAI use cases, including standard processes, framework, templates, libraries, and best practices around GenAI Serve as the expert and representative on LLMops Practices, including: (1) Developing and maintaining CI/CD pipelines for LLM deployment and updates. (2) Monitoring LLM performance, identifying and resolving bottlenecks, and implementing optimizations. (3) Ensuring the security of LLM operations through comprehensive risk assessments and the implementation of robust security measures. Collaborate with data and IT teams to facilitate data collection, preparation, and model training processes. Practical experience with training, tuning, utilizing LLMs/SLMs. Strong experience with GenAI/LLM frameworks and techniques, like guardrails, Langchain, etc. Knowledge of LLM security and observability principles. Experience of using Azure cloud services for ML Experience of using Azure cloud services for ML Min requirements: Programming languages: Python Public Cloud: Azure Frameworks: K8s, Terraform, Arize or any other ML/LLM observability tool Experience: Experience with public services like Open AI, Anthropic and similar, experience deploying open source LLMs will be a plus Tools: LangSmith/LangChain,guardrails Would be a plus: Knowledge of LLMOps best practices. Experience with monitoring/logging for production models (e.g. Prometheus, Grafana, ELK stack) We offer: Opportunity to work on bleeding-edge projects Work with a highly motivated and dedicated team Competitive salary Flexible schedule Benefits package - medical insurance, sports Corporate social events Professional development opportunities Well-equipped office

Project Description: Grid Dynamics wants to build a centralized, observable and secure platform for their ML, Computer Vision, LLM and SLM models. Grid Dynamics wants to onboard a vast number of AI agents, able to cover multiple required skills, ensuring a certain level of control and security in regards to their usage and availability. The observable platform must be vendor-agnostic, easy to extend to multiple type of AI applications and flexible in terms of technologies, frameworks and data types. This project is focused on establishing a centralized LLMOps capability where every ML, CV, AI-enabled application is monitored, observed, secured and provides logs of every activity. The solution consists of key building blocks such monitor every step in a RAG, Multimodal RAG or Agentic Platform, track performances and provide curated datasets for potential fine-tuning. Alignment with business scenarios, PepVigil provides also certain guardrails that allow or block interactions user-to-agent, agent-to-agent or agent-to-user. Also, Guardrails will enable predefined workflows, aimed to give more control over the series of LLM chains. Details on Tech Stack Job Qualifications and Skill Sets Advanced degree in Data Science, Computer Science, Statistics, or a related field Setting up Agent Mesh (LangSmith) Setting up Agent communication protocols (JSON/XML etc) Setting up message queues, CI/CD pipelines (Azure Queue Storage, Azure DevOps) Setting up integrations Langgrah, LangFuse Knowledge on Observability tool Arize-Phoenix tools Managing Agent Registry, Integrating with AgentAuth framework like Composio Setting up AgentCompute (Sandpack, E2BDev, Assistant APIs) Integration with IAM (Azure IAM, OKTA) Performing/Configuring Dynamic Orchestration and agent permissions Tech Stack Required: ML MLOPs Agent (Agent / Agent Mesh) LangFuse, LanChain, LangGraph Deployments (Docker, Jenkins, Kubernetes) Cloud Platforms: Azure/AWS/GCP We offer: Opportunity to work on bleeding-edge projects Work with a highly motivated and dedicated team Competitive salary Flexible schedule Benefits package - medical insurance, sports Corporate social events Professional development opportunities Well-equipped office