AI Product Engineer - Agentic AI Platforms (Financial Services)

Capgemini•Charlotte, NC

About The Position

Capgemini is at the forefront of Generative AI innovation, helping Financial Services clients industrialize GenAI and Agentic AI platforms at enterprise scale. We are seeking an experienced and innovative AI Product Engineer – Agentic Platforms to join our Financial Services Artificial Intelligence & Business Lines (FS‑ABL) practice. This role is ideal for a consulting technologist with deep expertise in modern GenAI tooling, agentic system design, and enterprise SDLC, who can partner directly with clients to envision, design, develop, and deploy Agentic AI platforms in regulated environments. In this role, you will work at the intersection of client advisory, AI product engineering, and delivery execution, helping banks, insurers, and capital markets firms transition from GenAI pilots to production‑grade, governed, multi‑agent systems. You will apply leading GenAI frameworks and LLM platforms — including Anthropic, OpenAI, LangChain, LangGraph, DSPy, and vector databases—while operating across the full Agentic SDLC. P&C Insurance knowledge and experience is a significant plus. Additionally, familiarity with core insurance platforms like Guidewire, DuckCreek or Majesco will be extremely helpful to succeed in this role. We are looking for candidates across all levels of experience and expertise - junior through senior level AI Product Engineers.

Requirements

Deep expertise in modern GenAI tooling, agentic system design, and enterprise SDLC
Experience with leading GenAI frameworks and LLM platforms — including Anthropic, OpenAI, LangChain, LangGraph, DSPy, and vector databases
Experience operating across the full Agentic SDLC
Experience building production‑grade AI services primarily using Python
Experience integrating GenAI agents with client systems via APIs, workflow engines, event streams, and data platforms.

Nice To Haves

P&C Insurance knowledge and experience
Familiarity with core insurance platforms like Guidewire, DuckCreek or Majesco

Responsibilities

Partner directly with Financial Services clients to identify, prioritize, and shape Agentic AI use cases across customer operations, underwriting, claims, risk, compliance, finance, and technology.
Lead client workshops to define agent personas, responsibilities, autonomy boundaries, human‑in‑the‑loop checkpoints, and escalation logic.
Translate evolving business needs into agentic product backlogs, roadmaps, and MVP definitions.
Support executive conversations around GenAI platform strategy, operating models, vendor selection, and scale‑out approaches.
Design and implement multi‑agent architectures using modern GenAI tooling, including: Planner, executor, reviewer/critic, and supervisor agents
Tool‑calling and function‑calling agents
Memory‑enabled agents (conversation, semantic, episodic, and structured memory)
Leverage LangChain and LangGraph for agent orchestration, workflows, and control flow.
Apply DSPy and declarative prompt optimization techniques for repeatability, performance tuning, and regression control.
Design agent interaction patterns such as hierarchical agents, collaborating agents, and event‑driven agent workflows.
Define standardized agent contracts, interfaces, and schemas to enable reuse and scale.
Own delivery across the full Software Development Lifecycle (SDLC), extending it into a formal Agentic SDLC, including:
Agent design specifications and behavior contracts
Prompt, policy, and tool versioning
Simulation environments and offline evaluation
Automated testing of agent flows and guardrails
Controlled rollout, telemetry‑driven optimization, and continuous learning
Build production‑grade AI services primarily using Python, integrating:
LLM providers such as Anthropic (Claude), OpenAI, and open‑source models
Retrieval‑Augmented Generation (RAG) using vector databases (e.g., Pinecone, FAISS, Milvus, Weaviate)
Implement CI/CD pipelines for agent code, prompts, and policies.
Integrate GenAI agents with client systems via APIs, workflow engines, event streams, and data platforms.
Implement agent observability including tracing, decision logging, tool usage, and failure analysis.
Apply evaluation frameworks for hallucination detection, consistency checks, and fitness scoring.
Design feedback loops incorporating human‑in‑the‑loop review and reinforcement.
Monitor cost, latency, throughput, and behavioral drift across deployed agents.
Design Agentic AI platforms aligned with Financial Services regulatory expectations, including:
Auditability and traceability of agent decisions
Model and prompt explainability
Data privacy and security controls
Resilience and fail‑safe mechanisms
Embed guardrails and policies addressing hallucination risk, bias, unauthorized actions, and escalation failures.
Produce documentation supporting risk, compliance, internal audit, and regulator engagement.
Provide technical leadership and mentorship to consulting delivery teams.
Contribute to internal GenAI accelerators, agent frameworks, and reusable assets.
Support RFPs, proposals, and client solution designs with credible GenAI and agentic architectures.
Participate in thought leadership on Agentic SDLC, GenAI engineering, and responsible autonomy.