Solution Architect Delivery & Engineering (Pune)

BaseBiz; Pune District; On-site; INR 3,500,000 - 6,000,000; Full time

Job summary

Zensar Technologies in Pune, India, is seeking a Solution Architect Delivery & Engineering to anchor AI delivery programs end-to-end. You will lead architecture, production deployment, and client engagements with senior executives, shaping AI-driven solutions in a rapidly evolving field.

The role demands hands-on design, coding, and leadership of delivery teams, with emphasis on LangChain, LangGraph, and RAG pipelines.

Qualifications

• Proven delivery of multi-agent AI systems in production.
• Experience with end-to-end AI delivery and CXO-level storytelling.
• Hands-on architecture, coding, and project leadership for AI programs.

Responsibilities

• Own end-to-end AI delivery from architecture to production deployment.
• Design and build multi-agent orchestration systems (LangChain, LangGraph, CrewAI).
• Integrate agents with enterprise surfaces: APIs, ERPs, CRMs, data platforms.
• Define agent topology: tool routing, memory strategy, state machines, fallback handling.
• Lead projects where AI writes significant portions of code and ship it.
• Mentor junior AI engineers and raise delivery quality.
• Stay current with models, frameworks, tooling; contribute to knowledge bases.

Skills

Agent Orchestration

LangChain / LangGraph

Agentic Coding

RAG & Vector Stores

LLM Platforms

Python / TypeScript

Observability (LangSmith)

Cloud Platforms

API & System Integration

CI/CD & DevOps

Tools

Claude Code CLI

Cursor

OpenAI Codex

Copilot

Job description

Solution Architect Delivery & Engineering Zensar Technologies | Pune, India

Location: Pune, India (Hybrid)

Level: Senior / Lead (10 to 15 years)

Reporting To: AVP Digital Transformation & AI

Employment Type: Full-Time

Department: AI & Digital Engineering

About the Role

This is not a slide‑making or prompt‑engineering role. We are looking for someone who has built multi‑agent AI systems that run in production—not demos, not pilots that died after a sprint. You will anchor AI delivery programs end‑to‑end, work directly with global clients, and stay sharp on a field that changes every few weeks.

You will report into and replicate the function of a senior AI delivery leader—meaning you need both the depth to architect solutions and the presence to walk a CXO through what you built and why it works.

Key Responsibilities

• Delivery & Architecture: Own end‑to‑end delivery of AI‑native programs—from architecture through production deployment.
• Design and build multi‑agent orchestration systems using LangChain, LangGraph, CrewAI, or equivalent.
• Integrate agent systems with enterprise surfaces: APIs, ERPs, CRMs, data platforms—rather than toy datasets.
• Define agent topology: tool routing, memory strategy, state machines, fallback handling.
• Agentic Coding & Development: Run agentic coding workflows using Claude Code, Cursor, OpenAI Codex, or equivalent CLI tools.
• Lead projects where AI writes significant portions of the codebase—guide, review, and ship it.
• Work with CLAUDE.md, shared context frameworks, and multi‑session agent setups for team use.
• Debug non‑deterministic agent outputs systematically—not by gut feel.
• Client & Stakeholder Engagement: Translate business problems into agent architectures for global CXO‑level stakeholders.
• Run discovery workshops, solution reviews, and delivery cadences with client teams.
• Prepare and present technical proposals, POC plans, and roadmaps—own the story end‑to‑end.
• Team & Practice: Mentor junior AI engineers; raise AI engineering quality across the delivery team.
• Stay current: evaluate recent models, frameworks, and tooling before the hype catches up.
• Contribute to internal knowledge bases, reusable frameworks, and accelerators.
• Client Communication: Can present architecture to a CXO without jargon.

Skills

• Agent Orchestration: LangChain, LangGraph, CrewAI—practical experience only.
• Agentic Coding Tools: Claude Code CLI, Cursor, OpenAI Codex, Copilot.
• RAG & Vector Stores: Chroma, Weaviate, Pinecone—know where RAG breaks LLM APIs & SDKs.
• LLM Platforms: Anthropic, OpenAI, Gemini—prompt design, tool use.
• Languages: Python, TypeScript—primary languages for agent and backend development.
• Observability: LangSmith—tracing, evaluation, debugging agent runs.
• Cloud Platforms: Azure, AWS, GCP (at least one)—deployment, infra, managed services.
• API & System Integration: REST, gRPC, Kafka—enterprise integration patterns.
• MCP / Shared Context: Model Context Protocol, CLAUDE.md, Beads—agent evaluation, testing non‑deterministic outputs, guardrails, evals.
• CI/CD & DevOps: Git, containers, pipelines—agents need to ship.

What You Must Have Actually Done

Not just what you know—what you have shipped.

• Deployed 23 agent‑based systems in production—stateful, multi‑step, real users.
• Used LangGraph for multi‑agent orchestration with memory, tool routing, and state management.
• Built projects where AI (Claude Code, Codex, Cursor) wrote significant portions of the code.
• Implemented RAG pipelines end‑to‑end—chunking, embedding, retrieval, re‑ranking, evaluation.
• Integrated agents with real enterprise APIs—not just OpenAI playground or sample data.
• Debugged a production agent failure—and fixed it without blaming the model.
• Can articulate when NOT to use agents—showing you have built things.

Bonus - Real Differentiators

• Experience with Claude Code CLI in team environments—CLAUDE.md, shared context, multi‑session flows.
• Familiarity with LangSmith—agent tracing, evaluation pipelines, debugging at scale.
• Has shipped using MCP (Model Context Protocol) or similar shared‑context tooling.
• QA/testing mindset for agents—systematic evaluation of non‑deterministic outputs.
• Background in IT services or consulting—managing client expectations while building.
• Experience with SLMs, fine‑tuning, or on‑device/edge agent deployment.

What We Are Not Looking For

• Someone who lists LLMs on a resume but has only called the API in a Jupyter notebook.
• AI enthusiasts whose hands‑on experience is less than a year old.
• People who explain everything in terms of frameworks they have never deployed.
• Consultants who can only narrate what others have built.

How We Will Evaluate You

Not a theory round. Expect to walk through something you have actually built—architecture decisions, what broke in production, and what you would do differently. If you cannot do that with specifics, this role is not the right fit.

Evaluation Stages

Stage 1 - Technical (content incomplete in source).