Forward Deployed Engineer (Senior level)

Cognizant; Muntinlupa; On-site; PHP 1,562,000 - 2,567,000; Full time

Job summary

Cognizant is seeking an experienced engineer to design, build, and deploy enterprise-grade AI agents using code-first frameworks. You will architect single/multi-agent patterns, implement tool calls, and ensure production readiness with grounding, memory, and RAG pipelines.

Responsibilities include integrating with enterprise systems, securing identities, and deploying through Teams and web channels. Requires 4+ years of experience, Python/C#, and willingness to work night shifts in Alabang.

Qualifications

• Bachelor's degree in CS or related field.
• At least 4 years of relevant experience.
• Experience delivering production LLM-based or agentic apps, not just prototypes.
• Strong Python and/or C#/.NET with clean API design.
• Hands-on with agent frameworks (Semantic Kernel, LangGraph/LangChain, Autogen).
• Deep prompt engineering: system prompts, few-shot patterns, structured output.
• RAG implementation with vector stores (Azure AI Search, Chroma, pgvector).
• Tool/function calling design including schema, validation, and failure recovery.
• Enterprise identity and API integration (Entra ID, OAuth 2.0).
• Must be amenable to night shift (8/9 PM–5/6 AM) and office 2–3x per week in Alabang.

Responsibilities

• Design agent architectures (single/multi/orchestrator).
• Build agents on Copilot Studio and code-first frameworks.
• Engineer instructions and deterministic guardrails for model behavior.
• Define tool calling with robust error handling and fallbacks.
• Implement human-in-the-loop checkpoints for risk decisions.
• Build agent memory and state management for conversations.
• Develop RAG pipelines: chunking, embeddings, vector indexing, retrieval.
• Connect agents to enterprise sources (SharePoint, Dataverse, Graph).
• Tune retrieval quality; diagnose grounding, hallucination and citation accuracy.
• Ensure source attribution for grounding evidence.
• Integrate agents with enterprise systems (ServiceNow, Graph, REST).
• Implement authentication/authorization patterns (Entra ID, SSO, least privilege).
• Deploy agents via Teams, M365 Copilot, web channels, or APIs.
• Build CI/CD pipelines with env promotion and version control.

Skills

Python

C# / .NET

System design

Prompt engineering

Night shift readiness

Office presence

Education

Bachelor's Degree in Computer Science or related field

Tools

Semantic Kernel

LangGraph

LangChain

Autogen

Azure AI Search

Chroma

pgvector

SharePoint

Dataverse

Graph connectors

REST APIs

Power Platform

Job description

Design, build, and deploy enterprise-grade AI agents using code-first frameworks, with strong focus on agent architecture, tool integration, grounding/RAG, and secure identity patterns. Ensure agents are production-ready through measurable evaluation, traceable source attribution, human-in-the-loop controls, CI/CD deployment, and stakeholder-driven delivery.

Job Responsibilities:

Agent Design & Build

• Design agent architectures - single-agent, multi-agent and orchestrator/worker patterns - selecting the right pattern for each use case.
• Build agents on Microsoft Copilot Studio and code-first frameworks (Semantic Kernel, LangGraph, LangChain, Autogen or equivalent).
• Engineer instructions, system prompts and reasoning flows; implement deterministic guardrails around non-deterministic model behavior.
• Define and implement tool/function calling - API actions, connectors, custom plugins - with robust error handling and fallback paths.
• Implement human-in-the-loop checkpoints, approval flows and escalation-to-human paths where decisions carry business or regulatory risk.
• Build agent memory and state management - conversation context, session state and long-term knowledge persistence.
• Build RAG pipelines: chunking strategy, embedding selection, vector indexing, hybrid and semantic retrieval, re-ranking.
• Connect agents to enterprise knowledge sources - SharePoint, Dataverse, Graph connectors, relational stores and document repositories.
• Tune retrieval quality and diagnose grounding failures, hallucination and citation accuracy issues.
• Implement source attribution so every agent answer is traceable to its grounding evidence.

Integration & Deployment

• Integrate agents with enterprise systems - ServiceNow, Microsoft Graph, Power Platform, REST APIs and internal services.
• Implement authentication and authorization patterns - Entra ID app registration, SSO, managed identity, delegated vs application permissions, least privilege.
• Deploy agents through Teams, M365 Copilot, web channels and API endpoints as the use case requires.
• Build CI/CD pipelines for agent solutions with environment promotion (dev → test → prod) and version control.

Qualifications:

• Bachelor's Degree or equivalent experience in Computer Science, Technology, or a related field of study
• Must have at least 4 years of relevant experience.
• Has experience in production delivery of at least two LLM-based or agentic applications - not prototypes or demos.
• Good working knowledge of Python and/or C#/.NET, with clean API design and solid software engineering fundamentals.
• Hands-on experience with an agent framework: Semantic Kernel, LangGraph/LangChain, Autogen, or equivalent.
• Deep prompt engineering skills: system prompt design, few-shot patterns, structured output, chain-of-thought control, instruction hierarchies.
• RAG implementation experience end to end, including vector stores (Azure AI Search, Chroma, pgvector or similar) and retrieval tuning.
• Tool/function calling design including schema definition, argument validation and failure recovery.
• Enterprise identity and API integration - Entra ID, OAuth 2.0, app registrations, scoped permissions.
• Must be amenable to work on a night shift schedule (8:00 PM to 5:00 AM or 9:00 PM to 6:00 AM)
• Must be amenable to work in the office at least 2-3x a week (Alabang)