Job Type: Contract
Work Mode: Remote
Job Description: Senior Generative & Agentic AI Engineer
Role Summary
We are looking for an experienced Senior Generative & Agentic AI Engineer / Technical Lead to design, develop and productionize custom Generative AI and Agentic AI solutions for enterprise use cases.
The role requires strong hands-on software engineering expertise, particularly in Python, along with practical experience building LLM-powered applications, AI agents, Retrieval-Augmented Generation (RAG), Knowledge Graph/GraphRAG solutions, tool-integrated workflows, APIs and cloud-native AI services.
The ideal candidate will be capable of taking AI solutions from concept and architecture through hands-on development, evaluation, deployment and production readiness, while ensuring security, scalability, reliability and responsible AI practices.
Key Responsibilities
Generative & Agentic AI Engineering
Design, develop and deploy custom Generative AI and Agentic AI applications using Python and modern AI frameworks.
Build AI agents capable of planning, reasoning, tool/function calling, state management, memory, multi-step execution and failure recovery.
Design single-agent and multi-agent architectures based on business and technical requirements.
Develop agent workflows using frameworks such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI or equivalent technologies.
Integrate agents with enterprise applications, APIs, databases, search platforms and external tools.
Implement human-in-the-loop approval and escalation patterns for sensitive or high-impact operations.
Develop reusable agent capabilities and services that can support multiple enterprise use cases.
RAG, Knowledge Graphs & Enterprise Knowledge
Design and implement production-grade Retrieval-Augmented Generation (RAG) solutions.
Develop document ingestion, parsing, chunking, embedding, metadata enrichment, indexing and retrieval pipelines.
Implement semantic, vector, keyword and hybrid search, reranking and retrieval optimization.
Design and integrate Knowledge Graphs to model enterprise entities, relationships and contextual knowledge.
Develop or integrate GraphRAG / Knowledge Graph-enhanced RAG solutions for relationship-aware retrieval and multi-hop reasoning.
Work with graph technologies such as Neo4j/Cypher or equivalent graph platforms, where appropriate.
Implement grounded responses, citations/source attribution and retrieval-quality evaluation.
Work with vector/search technologies such as Azure AI Search, pgvector, Pinecone, Weaviate, Milvus, FAISS or equivalent platforms.
LLM & AI Application Engineering
Develop applications using enterprise LLM platforms such as Azure OpenAI / Azure AI Foundry, Amazon Bedrock or equivalent services.
Evaluate and integrate commercial and open-weight LLMs based on business and technical requirements.
Implement prompt engineering, context engineering, structured outputs, tool/function calling and response validation.
Design model-routing and fallback strategies where multiple models are used.
Evaluate models based on quality, reasoning capability, latency, security, throughput and cost.
Apply fine-tuning or parameter-efficient approaches such as LoRA/PEFT when appropriate.
Agent Tools & Interoperability
Design secure interfaces that allow AI agents to interact with enterprise systems and tools.
Experience or familiarity with Model Context Protocol (MCP) for standardized integration between agents, enterprise data and tools.
Familiarity with emerging Agent-to-Agent (A2A) or equivalent interoperability patterns.
Implement secure tool discovery, invocation, authorization and auditability.
Design reusable tools and services that can be consumed by multiple agents.
Backend & Enterprise Integration
Develop scalable backend services and REST APIs using Python and FastAPI or comparable frameworks.
Integrate LLMs and AI agents with enterprise applications, APIs, databases and external data sources.
Design modular microservices and asynchronous/event-driven services where required.
Implement robust authentication, authorization, retries, timeouts, rate limiting and error handling.
Define API contracts, component boundaries and integration patterns.
Follow strong engineering practices covering modular development, automated testing, code quality, documentation and version control.
AI Evaluation, Reliability & Observability
Design evaluation strategies for LLM, RAG and Agentic AI applications.
Build automated evaluation and regression test suites.
Evaluate AI solutions across:
Response quality and correctness
Groundedness and hallucination
Retrieval relevance
Tool selection and execution
Agent task completion
Latency, token consumption and cost
Implement guardrails, output validation and fallback mechanisms.
Implement tracing of agent execution, LLM interactions and tool calls.
Establish logging, monitoring and observability for production AI applications.
Support adversarial testing and AI security validation.
AI Security & Responsible AI
Design AI applications according to secure-by-design and Responsible AI principles.
Implement identity, authentication, authorization, RBAC, secrets management and least-privilege access.
Implement permission-aware access to enterprise knowledge and agent tools.
Design controls against prompt injection, indirect prompt injection, data leakage, unauthorized retrieval and unsafe tool execution.
Implement auditability for agent decisions and actions.
Support appropriate human oversight for consequential AI-generated actions.
Collaborate with enterprise security, architecture and governance teams during production readiness.
Cloud, DevOps & LLMOps
Build and deploy AI applications on Azure, AWS or equivalent enterprise cloud environments.
Containerize services using Docker and use Kubernetes where appropriate.
Implement CI/CD pipelines and automated deployment practices.
Apply MLOps/LLMOps practices covering application, prompt, model, agent and configuration versioning.
Implement production monitoring, tracing and operational support.
Optimize AI applications for performance, latency, scalability, reliability and cost.
Architecture & Technical Leadership
Translate business requirements into practical AI solution architectures and implementation plans.
Determine when a problem requires traditional software, workflow automation, RAG, Knowledge Graphs, Agentic AI or a combination of approaches.
Convert high-level architectures into low-level designs, component boundaries, APIs and implementation plans.
Lead technical design discussions and code reviews.
Establish reusable engineering standards and patterns for AI application development.
Guide developers through design, implementation, testing and production readiness.
Rapidly prototype and evaluate emerging AI technologies for enterprise adoption.
Clearly communicate technical trade-offs, risks and limitations to technical and business stakeholders.
Required Skills & Qualifications
8+ years of relevant professional experience in software engineering, AI engineering or solution architecture.
Strong hands-on Python programming expertise.
Experience developing backend services using FastAPI, Django or comparable Python frameworks.
Hands-on experience developing Generative AI and LLM-powered applications.
Practical experience designing and implementing Agentic AI applications and workflows.
Experience with an agent/orchestration framework such as LangGraph, LangChain, Semantic Kernel, AutoGen, CrewAI or equivalent.
Strong knowledge of RAG architecture and implementation.
Strong understanding of:
Embeddings
Vector databases
Semantic/hybrid search
Information retrieval
Reranking
Prompt/context engineering
Experience integrating LLMs and AI agents with enterprise APIs, databases and external systems.
Experience deploying applications in at least one major cloud environment, preferably Azure and/or AWS.
Understanding of secure, scalable and production-grade software engineering.
Experience with REST APIs, Git, automated testing and CI/CD.
Strong analytical, problem-solving and communication skills.