: Agentic AI Engineering - Lead Programmer Analyst (Exp: 5 Yrs to 7 Yrs)

Design and deliver LLM applications and agents that retrieve enterprise knowledge, use tools and complete business workflows reliably. Remain hands-on in architecture, implementation and debugging while guiding junior engineers. The role focuses on applications built with existing models; traditional predictive-model training is not a core requirement.

Required Experience And Technical Skills

- 5+ years of professional software or data engineering experience, including hands-on delivery of LLM applications and agentic AI workflows.

- Solid Python and SQL; API development with FastAPI or Flask, validation with Pydantic, and asynchronous service integration.

- Practical experience with LLM APIs, streaming, token limits, prompt design, schema validation and model selection.

- Hands-on LangChain experience or equivalent frameworks; ability to choose between fixed workflows and agent decisions.

- RAG development using LangChain or LlamaIndex and vector stores such as pgvector or Qdrant, with filters and retrieval evaluation.

- Ability to implement tool calling, persistent state, context and memory management, approval flows and reliable error handling.

- Experience with AI evaluation, observability, access controls and secure tool execution, plus Git, testing, containers and cloud deployment.

Key Responsibilities

- Translate business workflows into clear agent responsibilities, tool interfaces, success criteria and approval boundaries.

- Build LLM applications using effective prompts,



structured outputs and context management; choose models based on quality, latency and cost.

- Develop RAG pipelines covering document ingestion, chunking, embeddings, hybrid retrieval, reranking and source-grounded answers.

- Implement tool-using workflows with state, memory, checkpoints, human approvals, retries and safeguards against repeated actions or endless loops.

- Integrate business APIs and data sources; enforce permissions and protect against prompt injection and sensitive-data exposure.

- Build evaluation datasets, regression checks and traces; debug failures and improve task completion, response time and operating cost.

- Own implementation quality and delivery while coaching juniors through design, coding, testing and production troubleshooting.

Mentoring And Technical Ownership

- Demonstrated ability to groom and guide junior engineers through pairing, design discussions, code reviews and constructive feedback.

- Define tasks and acceptance criteria, remove technical blockers and review individual progress toward independent delivery.

- Build reusable agent components and practical documentation; explain design choices and delivery risks to stakeholders.

Preferred Skills

- Exposure to CrewAI / LangGraph for agent orchestration and multi-agent workflows; MCP integration and multimodal applications.

- Exposure to Langfuse, LangSmith or equivalent tracing and evaluation tools; prompt/version management and evaluation gates.

- Hugging Face Transformers for open-model integration; caching and model routing. Frameworks listed are alternatives; mastery of every tool is not required.

📌 Agentic AI Engineering - Lead Programmer Analyst (Exp: 5 Yrs to 7 Yrs) (Hyderabad)
🏢 BILVANTIS TECHNOLOGIES
📍 Hyderabad