GenAI Engineer / AI Agent Engineer – AI Foundry & Copilot Studio
At a glance
Mid-level AI Engineering role at Dxctechnology. Mumbai · full-time.
Pay not stated AI Engineering salary
aimlroles summary, based on the employer's posting.
What you'll do
- Build and deploy agents in AI Foundry and Copilot Studio, including tool use, planning, memory and safety controls
- Connect agents to enterprise documents and systems, then improve retrieval, citations and source traceability
- Test agent quality and track traces, tool activity, latency, cost and failure patterns in production
- Apply access controls, secrets handling, privacy safeguards and audit practices to GenAI solutions
- Turn stakeholder needs into agent designs and contribute reusable development patterns
What you bring
- Three to five years building software, with production deployment experience in Python, Java, TypeScript or a similar language
- Practical experience creating and deploying AI Foundry and Copilot Studio agents with integrated tools
- Strong grounding in LLM prompting, RAG, embeddings, vector search and retrieval techniques
- Experience connecting GenAI systems to REST APIs, microservices, message queues and databases
Who this fits
This mid-level role suits a software engineer who has taken agent-based GenAI systems into production and can work across retrieval, integrations and testing. The role is based in Mumbai and emphasizes in-person collaboration, with flexibility also noted.
From the employer
Job Description:
Key Responsibilities
AI Agents & GenAI Solution Development
- Design, build, and deploy AI agents using Foundry + Studio to solve real business problems
- Implement core agent capabilities:
- Tool/function calling, multi-step planning, task decomposition
- Retrieval-Augmented Generation (RAG) with enterprise knowledge sources
- Memory patterns (session/state, long-term memory with governance)
- Guardrails (policy checks, prompt safety, structured outputs)
- Develop agent workflows integrating:
- APIs, databases, event-driven services, internal tools
- Approval loops, HITL (Human-in-the-Loop), and escalation handling
Data & Knowledge Integration
- Build and optimize RAG pipelines:
- Document ingestion, chunking, embedding strategies
- Vector search
- Grounding, citations, and source traceability
- Connect enterprise data sources in AI Foundry (datasets, ontology/semantic models where applicable) and operationalize for agent usage.
Engineering Excellence (Production Readiness)
- Create evaluation frameworks for GenAI:
- Automated tests for factuality/grounding, relevance, toxicity, refusal correctness
- Offline + online evaluation, regression testing for prompts and agent tools
- Implement observability:
- Agent traces, tool-call logs, latency/cost metrics, failure modes
- Ensure security, compliance, and governance:
- Access control, secrets management, PII handling
- Model usage policies, auditability, and change management
Collaboration & Delivery
- Partner with stakeholders to translate requirements into agent designs and deliver measurable outcomes.
- Contribute to reusable libraries, templates, and best practices for Foundry/Studio agent development.
Required Qualifications (Must-Have)
- 3–5 years in software engineering (Python/Java/TypeScript or similar) with production deployment experience.
- Hands-on experience building AI agents in AI Foundry and Copilot Studio (agent workflows, tool integration, deployment).
- Strong understanding of LLMs and prompting patterns:
- System prompts, structured outputs (JSON), function/tool calling, chain-of-thought-safe patterns
- Solid experience with RAG and search:
- Embeddings, vector databases/search, chunking, reranking, grounding techniques
- Experience integrating GenAI solutions with:
- REST APIs, microservices, message queues, databases
- Familiarity with software engineering best practices:
- Unit/integration testing, CI/CD, code reviews, documentation
Preferred Qualifications (Nice-to-Have)
- Experience with one or more agent frameworks/concepts:
- LangGraph/LangChain, Semantic Kernel, AutoGen-style orchestration patterns
- Experience with model providers and deployment patterns:
- Azure OpenAI / OpenAI / open-source models
- Exposure to governance and compliance in enterprise AI:
- Data classification, audit logging, model risk management
Core Technical Skills (Current GenAI Stack)
- Languages: Python (preferred), Java/TypeScript (plus)
- GenAI/LLM: Prompt engineering, tool calling, structured outputs, safety patterns
- AI Foundry & Copilot Studio: Building pipelines, deploying apps/workflows/agents, access controls
- Agents: Planning + tools + memory + orchestration; multi-agent (optional)
- RAG: Embeddings, retrieval strategies, reranking, grounding/citations
- Evaluation: Golden datasets, automated evals, human review loops, regression testing
- MLOps/DevOps: CI/CD, containerization, monitoring, performance/cost optimization
At DXC Technology, we believe strong connections and community are key to our success. Our work model prioritizes in-person collaboration while offering flexibility to support wellbeing, productivity, individual work styles, and life circumstances. We’re committed to fostering an inclusive environment where everyone can thrive.
Recruitment fraud is a scheme in which fictitious job opportunities are offered to job seekers typically through online services, such as false websites, or through unsolicited emails claiming to be from the company. These emails may request recipients to provide personal information or to make payments as part of their illegitimate recruiting process. DXC does not make offers of employment via social media networks and DXC never asks for any money or payments from applicants at any point in the recruitment process, nor ask a job seeker to purchase IT or other equipment on our behalf. More information on employment scams is available here.