Gen AI Specialist – AI Consulting & Strategy

Experience : 5+ Years Experience
Education : Bachelor’s/Master’s degree
Work Location : Chennai, India (Chennai/Remote/Hybrid)

Key Responsibilities :

• Architect multi-agent and orchestration frameworks to support diverse AI-driven workflows.
• Develop modular agent ecosystems that communicate, plan, and reason collaboratively.
• Implement retrieval and reasoning pipelines optimized for enterprise-scale workloads.
• Collaborate with Data Engineers and LLM Engineers to integrate model intelligence with institutional data layers.
• Define AI evaluation metrics and implement continuous improvement cycles for generative pipelines.
• Lead proof-of-concept projects demonstrating agentic orchestration for real-world use cases.

Required Technical Skills :

Agentic System Architecture

• Expertise in designing multi-agent orchestration using LangChain, LlamaIndex, AutoGen, or CrewAI.
• Deep understanding of agent communication, memory, and goal-directed planning.
• Ability to decompose complex workflows into agent tasks and coordination layers.

Generative AI Development

• Hands-on experience building applications using OpenAI, Anthropic, Mistral, or local LLMs.
• Proficiency in prompt design, retrieval-augmented generation (RAG), and tool use orchestration.
• Familiarity with generation control techniques (chain-of-thought prompting, self-correction, context pruning).

Knowledge & Retrieval Layer

• Expertise in RAG architecture, embedding optimization, and retrieval performance tuning.
• Experience with vector databases such as Pinecone, Milvus, Weaviate, FAISS, or Chroma.
• Integration experience with document loaders, retrievers, and knowledge graph interfaces.

Workflow Orchestration & Integration

• Build end-to-end agentic pipelines integrating APIs, third-party services, and internal business logic.
• Implement tool orchestration, event-driven workflows, and async agent task handling.
• Experience with workflow engines (Temporal, Airflow, Prefect) for agent coordination.

Evaluation & Optimization

• Design and apply AI evaluation frameworks for accuracy, context coherence, and safety.
• Apply reinforcement learning, feedback loops, and adaptive policy mechanisms to improve agent behavior.
• Optimize latency, token usage, and cost efficiency across LLM-driven workflows.

Programming & Infrastructure

• Strong coding skills in Python and familiarity with TypeScript or Go for orchestration scripting.
• Experience with containerization (Docker, Kubernetes) and cloud AI infrastructure (AWS, Azure, GCP, or OCI).
• Knowledge of model APIs, SDKs, and plugin architectures for integrating AI agents into enterprise systems.

Required Skills & Experience :

• 5+ years of experience in AI/ML or software engineering, with at least 2 years focused on generative AI systems.
• Proven expertise in LLM orchestration frameworks and RAG-based architectures.
• Deep understanding of prompt optimization, context chaining, and retrieval pipelines.
• Experience building multi-agent systems or adaptive reasoning frameworks.
• Proficiency with LangChain, LlamaIndex, or CrewAI in production-grade environments.
• Solid foundation in API development, cloud integration, and orchestration patterns.