Walk-in | Python+ Generative AI

Lancesoft; Bengaluru; Hybrid; INR 3,500,000 - 7,000,000; Full time

Job summary

Lancesoft is seeking a Senior GenAI Engineer to design and build agentic applications—multi-step, tool-using LLM systems that solve enterprise workflows. You will own the agent layer end-to-end: prompts, orchestration graphs, tool integration, evaluation, and production hardening.

This role requires LangChain/LangGraph production experience on a managed cloud LLM platform. You will design RAG pipelines, integrate tools, and implement guardrails, with collaboration across platform, product, and

Qualifications

• 5–8 years of overall engineering experience with strong Python fluency.
• 2+ years hands-on with LLM application development beyond demos.
• Production experience with LangChain and LangGraph—built, debugged, shipped agents.
• Experience on AWS Bedrock, Azure AI Foundry, or Google Vertex AI with native APIs.
• Knowledge of RAG architectures and at least one vector database.
• Proficiency in prompt engineering, function/tool calling, and JSON outputs.
• Familiarity with evaluation/observability tools for LLM apps and enterprise protocols.

Responsibilities

• Design and build agentic applications with LangChain and LangGraph.
• Develop multi-agent workflows with planning, tool use, memory, and human-in-the-loop.
• Operate solutions on Bedrock, Foundry, or Vertex AI including guardrails.
• Engineer RAG pipelines, embeddings, retrieval, and grounding strategies.
• Create and integrate tools/functions that agents call via APIs or databases.
• Define evaluation harnesses and metrics for regression and quality.
• Implement input/output validation, PII handling and cost/latency controls.
• Collaborate with platform teams to productionize agents and with domain experts.

Skills

Python

LLM development

LangChain

LangGraph

AWS Bedrock

Azure AI Foundry

Vertex AI

RAG architectures

Tools

APIs

Databases

MCP servers

Job description

Role & responsibilities

Senior Generative & Agentic AI Engineer

Experience:58 years (at least 2 years hands-on with LLMs and agents)

Location:Bengaluru / HybridTrack:Generative AI & Agentic Systems

Role Summary

We are hiring a SeniorGenAIEngineer to design and build agentic applications — multi-step, tool-using LLM systems that solve real enterprise workflows. You will own the agent layer end-to-end: prompt design, orchestration graphs, tool integration, evaluation, and production hardening. This role is for engineers who have moved beyond chat wrappers and have shipped LangChain/LangGraph agents on a managed cloud LLM platform in production.

What You’ll Do

• Design and buildagentic applicationswithLangChain and LangGraph— multi-agent workflows with planning, tool use, memory, and human-in-the-loop checkpoints.
• Build and operate solutions onAWS Bedrock, Azure AI Foundry, or Google Vertex AI— model selection, invocation, streaming, guardrails, and platform-native agent capabilities (Bedrock Agents/AgentCore, Foundry Agent Service, Vertex AI Agent Builder).
• EngineerRAG pipelines— chunking strategies, embeddings, hybrid retrieval, reranking, and grounding — using the chosen cloud's managed services or OSS equivalents.
• Build and integratetools/functionsthat agents call (APIs, databases, MCP servers, internal systems).
• Define and runevaluation harnesses— golden sets, LLM-as-judge, RAGAS-style metrics, regression suites.
• Implement guardrails: input/output validation, PII handling, prompt-injection defenses, cost and latency controls.
• Collaborate with thePythonplatform team to productionize agents reliably; partner with product and domain experts on use-case framing.
• Stay current with the model and tooling landscape, and advise on build-vs-buy and model-routing decisions.

Must-Have Skills

• 5–8 years of overall engineering experience, withstrongPythonfluency.
• 2+ years hands-on with LLM application development— beyond chatbot demos.
• Mandatory: production experience with LangChain and LangGraph— built, debugged, and shipped agents using both. LangGraph state machines, checkpointers, and tool-node patterns should be familiar territory.
• Mandatory: hands-on production experience on at least one of—AWS Bedrock, Azure AI Foundry (incl. Azure OpenAI), or Google Vertex AI. Must have used the platform's native model APIs, agent/orchestration features, and guardrail capabilities — not just called the underlying models.
• Working knowledge ofRAG architecturesand at least onevector database(Pinecone, Weaviate, pgvector, OpenSearch, FAISS, Milvus, or the chosen cloud's managed equivalent).
• Practical command ofprompt engineering, function/tool calling, structured outputs (JSON schema), and context-window management.
• Familiarity withevaluation and observabilityfor LLM apps (RAGAS, LangSmith, Langfuse, Phoenix, or custom harnesses).
• Awareness of emerging protocols —MCP, A2A, or similar— and how agents integrate with enterprise tools.

Nice-to-Have

• Experience withstreaming, async orchestration, and long-running agent execution patterns.
• Exposure to a second cloud's AI platform (useful, not required).
• Exposure to fine-tuning, LoRA/QLoRA, or model distillation.
• Background in regulated domains (BFSI, healthcare) and familiarity with AI governance frameworks.
• Open-source contributions or technical writing in theGenAIspace.

Preferred candidate profile