Lead Generative AI & Agentic AI Engineer

• Location: No Location Set
• Type: Contract
• Job #35696

Lead Generative AI & Agentic AI Engineer

Contract: 6 Months + Extension
Location: 100% Remote – North or South America
Hours: 37.5 Hours per Week
Start: Early September

Position Overview

We are seeking a Lead Generative AI & Agentic AI Engineer to support the design and delivery of enterprise AI solutions within a financial services environment.

This is a senior, hands-on engineering role focused on turning AI architecture and business requirements into production-quality applications, services, APIs, retrieval pipelines, agent workflows, orchestration components, and reusable AI engineering capabilities.

The successful candidate will bring strong expertise across Generative AI, Agentic AI, Python, Retrieval-Augmented Generation (RAG), LLM application development, agent orchestration, tool integration, intelligent document processing, evaluation, and production AI engineering.

This is not a research, notebook-only, or proof-of-concept role. The Lead Engineer will contribute substantial production code throughout the engagement and own components through development, testing, controlled deployment, defect resolution, optimization, and production stabilization.

The role will work closely with AI Architects, Data Engineers, Infrastructure/Platform teams, and business stakeholders, while providing technical leadership and maintaining a strong client-facing presence.

Key Responsibilities

Generative AI & Agentic AI Engineering

• Lead the detailed technical implementation of Generative AI and Agentic AI solutions supporting enterprise business use cases.
• Translate solution architecture and business requirements into production-ready Python services, APIs, libraries, workflows, and reusable engineering components.
• Design and implement LLM-powered applications and agentic workflows, including:
  • Agent instructions and orchestration
  • Structured outputs
  • State and memory management
  • Context management
  • Tool selection and execution
  • Multi-step agent workflows
• Engineer secure integrations with enterprise functions, APIs, services, and MCP-based tools.
• Develop reusable AI engineering patterns and components that can support multiple business use cases.

RAG, Retrieval & Knowledge Engineering

• Design and implement Retrieval-Augmented Generation (RAG) pipelines and supporting knowledge-preparation processes.
• Build and optimize:
  • Vector search
  • Keyword search
  • Hybrid retrieval
  • Metadata filtering
  • Reranking
  • Grounded-response behaviour
• Develop ingestion and knowledge-preparation pipelines that enable accurate and reliable retrieval across enterprise information sources.
• Diagnose and improve retrieval quality, relevance, groundedness, and response accuracy.

Intelligent Document & Multimodal Processing

• Develop AI capabilities supporting intelligent document processing, including:
  • OCR
  • Layout analysis
  • Information extraction
  • Document classification
  • Document comparison
  • Multimodal processing
• Implement confidence scoring, validation, exception handling, and human-review routing where appropriate.
• Engineer reliable processing workflows for complex and unstructured enterprise information.

AI Evaluation, Testing & Quality

• Build representative evaluation datasets for AI applications and use cases.
• Develop automated evaluation and regression frameworks covering:
  • Retrieval quality
  • Groundedness
  • Extraction accuracy
  • Agent trajectories
  • Tool execution
  • Safety
  • Overall task success
• Establish strong coding, testing, validation, and engineering quality practices.
• Diagnose failures across model, retrieval, agent, data, integration, and API boundaries.
• Optimize AI solutions based on measurable evidence across quality, latency, throughput, reliability, and cost.

Production Engineering & Delivery

• Own contributed components throughout the full production lifecycle, from development through deployment and stabilization.
• Ensure solutions move beyond demonstrations and proof-of-concepts into tested, maintainable, production-quality implementations.
• Support controlled code changes, deployment, troubleshooting, defect resolution, and production stabilization.
• Review implementation quality and help establish reusable engineering standards and practices.

Architecture & Cross-Functional Collaboration

• Partner closely with the AI Solution Architect to translate platform and architectural blueprints into working technical solutions.
• Develop reusable services, APIs, libraries, agent patterns, orchestration components, and evaluation capabilities.
• Work directly with data, cloud, infrastructure, and platform teams to resolve dependencies involving:
  • Data access and schemas
  • Data pipelines
  • Compute and serving
  • Networking
  • Runtime environments
  • Enterprise integrations
• Communicate effectively with both technical teams and client stakeholders, providing clear technical direction and recommendations.

Required Qualifications
 

• Senior-level experience in software engineering, AI/ML engineering, or applied AI, with demonstrated technical leadership responsibilities.
• Strong hands-on experience building Generative AI / LLM applications beyond proof-of-concept environments.
• Demonstrated experience with Agentic AI, AI agents, or multi-step LLM workflows.
• Advanced hands-on development skills in Python.
• Strong experience developing production services, APIs, libraries, and integration components.
• Hands-on experience designing and implementing RAG and enterprise retrieval solutions.
• Understanding of vector, keyword and hybrid search, metadata filtering, reranking, and grounding techniques.
• Experience with prompt engineering, context engineering, model behaviour, structured outputs, state and memory management.
• Experience integrating AI solutions with APIs, enterprise systems, functions, and external tools.
• Strong understanding of AI evaluation, testing, regression testing, quality measurement, and production monitoring.
• Ability to troubleshoot complex issues across LLMs, retrieval systems, agents, data pipelines, APIs, and application components.
• Experience taking AI solutions through deployment, production support, optimization, and stabilization.
• Strong technical communication skills with the ability to work directly with clients, architects, engineers, and business stakeholders.

Highly Relevant Experience

Experience in one or more of the following would be particularly valuable:

• Model Context Protocol (MCP) and tool-based agent integrations
• Intelligent Document Processing (IDP)
• OCR and document layout analysis
• Multimodal AI solutions
• Human-in-the-loop / human-review workflows
• Enterprise knowledge and retrieval platforms
• AI evaluation and automated quality frameworks
• Production AI observability and performance optimization
• Reusable enterprise AI platforms, frameworks, or shared services
• Financial services, banking, or credit union environments

What We’re Looking For

The ideal candidate is a senior AI engineer who still codes extensively and can combine technical leadership with hands-on delivery. You should be comfortable moving between architecture, Python development, RAG, agents, APIs, evaluation, debugging, optimization, and client-facing technical discussions.

Success in this role means delivering AI capabilities that are not simply impressive demonstrations, but reliable, testable, reusable, secure, and production-ready solutions that solve real business problems.