Senior AI Developer Experience: 4 - 6 Years Exp Salary : INR 20-30 Lacs per annum Preferred Notice Period : Within 60 Days Shift : 2:30PM to 11:30PM IST Opportunity Type: Hybrid (Hyderabad) Placement Type: Permanent (*Note: This is a requirement for one of Uplers' Clients) Must have skills required : AI RAG, Fast or Flask API, Vector DB, postgresql, Python, Langchain OR Llama Good to have skills : Grafana or Prometheus, Docker, Kubernetes K-3 Innovations (One of Uplers' Clients) is Looking for: Senior AI Developer who is passionate about their work, eager to learn and grow, and who is committed to delivering exceptional results. If you are a team player, with a positive attitude and a desire to make a difference, then we want to hear from you. Role Overview Description About K3-Innovations K3-Innovations, Inc. is building a cutting-edge, AI-driven SaaS platform that automates critical workflows in the biopharma industry. We are expanding our team with an AI RAG Engineer who will help us design and optimize retrieval-augmented generation (RAG) pipelines for knowledge workflows. This role combines deep expertise in database design, vector search optimization, backend architecture, and LLM (Large Language Model) integration. You will play a key role in building a scalable AI platform, bridging structured and unstructured biopharma data with next-generation AI. If you're passionate about building intelligent retrieval systems, fine-tuning prompt pipelines, and optimizing LLM-based applications for real-world datasets, we want to hear from you! Key Responsibilities 1. RAG Pipeline Design and Optimization (Priority #1) Architect and implement retrieval-augmented generation pipelines integrating document retrieval and LLM response generation. Design and maintain knowledge bases and vector stores using tools like FAISS, Weaviate, or PostgreSQL PGVector. Optimize retrieval mechanisms (chunking, indexing strategies, reranking) to maximize response accuracy and efficiency. Integrate context-aware querying from structured (Postgres) and unstructured (text/PDF) sources. 2. Database and Embedding Management Design relational schemas to support knowledge base metadata and chunk-level indexing. Manage embeddings pipelines using open-source models (e.g., HuggingFace sentence transformers) or custom embedding services. Optimize large-scale vector search performance (indexing, sharding, partitioning). 3. LLM and Prompt Engineering Develop prompt engineering strategies for retrieval-augmented LLM pipelines. Experiment with prompt chaining, memory-augmented generation, and adaptive prompting techniques. Fine-tune lightweight LLMs or integrate APIs from OpenAI, Anthropic, or open-source models (e.g., LlamaIndex, LangChain). 4. Backend API and Workflow Orchestration Build scalable, secure backend services (FastAPI/Flask) to serve RAG outputs to applications. Design orchestration workflows integrating retrieval, generation, reranking, and response streaming. Implement system monitoring for LLM-based applications using observability tools (Prometheus, OpenTelemetry). 5. Collaboration and Platform Ownership Work closely with platform architects, AI scientists, and domain experts to evolve the knowledge workflows. Take ownership from system design to model integration and continuous improvement of RAG performance. Required Skills AI RAG Engineering (Most Critical) Knowledge Retrieval: o Experience building RAG architectures in production environments. o Expertise with vector stores (e.g., FAISS, Weaviate, Pinecone, PGVector). o Experience with embedding models and retrieval optimization strategies. Prompt Engineering: o Deep understanding of prompt construction for factuality, context augmentation, and reasoning. o Familiarity with frameworks like LangChain, LlamaIndex, or Haystack. Database and Backend Development (Essential) PostgreSQL Expertise: o Strong proficiency in relational and vector extension design (PGVector preferred). o SQL optimization, indexing strategies for large datasets. Python Development: o Experience building backend services using FastAPI or Flask. o Proficiency with async programming and API integrations. Observability and DevOps (Supportive) System monitoring for AI workflows using Prometheus, Grafana, OpenTelemetry. Familiarity with Docker, Kubernetes-based deployment pipelines. Preferred Experience (Bonus but not Required) Working with large-scale scientific or healthcare datasets. Exposure to clinical standards like SDTM, ADaM (advantageous for biopharma workflows). Experience integrating domain-specific ontologies into retrieval systems. Familiarity with fine-tuning LLMs on private knowledge bases. What Were Looking For AI Problem Solver: You are excited by combining retrieval, reasoning, and generative capabilities to solve real-world problems. Backend and Data Specialist: You understand database performance and scalable architectures for retrieval and serving. Builder's Mindset: You thrive in dynamic, evolving environments where you can architect and implement end-to-end solutions. What We Offer Meaningful Impact: Build AI systems that accelerate workflows in the critical biopharma space. Technical Growth: Deepen your expertise in retrieval-augmented generation and scalable AI systems. Remote Flexibility: Results-driven work culture with location flexibility. Competitive Compensation: Attractive salary, benefits, and learning opportunities. Join Us Help us revolutionize how biopharma manages and accesses knowledge through the power of AI. How to apply for this opportunity: Easy 3-Step Process: 1. Click On Apply! And Register or log in on our portal 2. Upload updated Resume & Complete the Screening Form 3. Increase your chances to get shortlisted & meet the client for the Interview! About Our Client: K3-Innovations is redefining clinical research with a strategic scaling approach, blending AI-powered automation, adaptive clinical resourcing, and advanced data science. As a next-generation CRO, we provide flexible FSP models, regulatory-compliant statistical programming, and AI-driven analytics to accelerate clinical trial execution and regulatory submissions. About Uplers: Our goal is to make hiring and getting hired reliable, simple, and fast. Our role will be to help all our talents find and apply for relevant product and engineering job opportunities and progress in their career. (Note: There are many more opportunities apart from this on the portal.) So, if you are ready for a new challenge, a great work environment, and an opportunity to take your career to the next level, don't hesitate to apply today. We are waiting for you!
