End -to -end design, development, and deployment of enterprise -grade AI solutions leveraging Azure AI, Google Vertex AI, or comparable cloud platforms. <\/div>
• <\/div>
Architect and implement advanced AI systems, including agentic workflows, LLM integrations, MCP -based solutions, RAG pipelines, and scalable microservices. <\/div>
• <\/div>
Oversee the development of Python -based applications, RESTful APIs, data processing pipelines, and complex system integrations. <\/div>
• <\/div>
Define and uphold engineering best practices, including CI/CD automation, testing frameworks, model evaluation procedures, observability, and operational monitoring. <\/div>
• <\/div>
Partner closely with product owners and business stakeholders to translate requirements into actionable technical designs, delivery plans, and execution roadmaps. <\/div>
• <\/div>
Provide hands -on technical leadership, conducting code reviews, offering architectural guidance, and ensuring adherence to security, governance, and compliance standards. <\/div>
• <\/div>
Communicate technical decisions, delivery risks, and mitigation strategies effectively to senior leadership and cross -functional teams. <\/div>
Required Skills & Experience <\/div>
LLM & Core AI <\/div>
• <\/div>
Strong understanding of transformers (attention, tokens, context window) and LLM behavior. <\/div>
• <\/div>
Hands -on with 2+ LLM providers (e.g., Azure OpenAI + Anthropic / open source like Llama/Qwen). <\/div>
Built context builders that select relevant history (recency + semantic) and inject tool + RAG outputs. <\/div>
• <\/div>
Implemented context compression (conversation/memory summarization) and structured outputs (JSON/schema) with robust error handling. <\/div>
Tools, MCP & External Integrations <\/div>
• <\/div>
Designed and implemented LLM tools/function schemas with validation, clear errors, and safe side -effects. <\/div>
• <\/div>
Hands -on experience with MCP (Model Context Protocol): building MCP servers/tools for internal data and actions, including auth and multi -tenant isolation. <\/div>
• <\/div>
Experience integrating REST/SQL/sandboxed execution tools and defining fallback/degradation strategies when tools fail. <\/div>
Agentic Systems, Orchestration & A2A <\/div>
• <\/div>
Built multi -step agentic workflows: plan â tool calls â intermediate decisions â final answer. <\/div>
• <\/div>
Practical use of agent roles (Planner / Worker / Critic / Router / Supervisor). <\/div>
• <\/div>
Hands -on with A2A (Agent -to -Agent) collaboration where specialist agents exchange structured state. <\/div>
• <\/div>
Experience with at least one agentic/workflow framework (e.g., LangGraph, LangChain agents, Google ADK, Orkes Conductor, Temporal) and checkpointed, resumable flows (Postgres/Redis). <\/div>
Experience with query rewriting/expansion and grounded answers with citations, including debugging retrieval quality. <\/div>
Reasoning, Evaluation & Guardrails <\/div>
• <\/div>
Implemented ReAct -style and tool -augmented reasoning patterns, including self -critique/second -pass flows. <\/div>
• <\/div>
Defined task -level success metrics and built golden test flows from real logs to evaluate prompt/model/flow changes. <\/div>
• <\/div>
Instrumented telemetry for tool errors, step counts, loops, latency, and cost (tokens, per feature/tenant). <\/div>
• <\/div>
Implemented guardrails: prompt -injection defenses, per -tenant/per -role tool & data access, input/output filtering, PII -safe logging, and participated in red -teaming/adversarial testing. <\/div>
Model, Cost & Performance Engineering <\/div>
• <\/div>
Experience choosing and combining small router/classifier models with large reasoning models. <\/div>
• <\/div>
Implemented caching (LLM outputs, retrieval results) and optimized latency (parallelization, step count, time budgets). <\/div>
• <\/div>
Built or contributed to cost/usage monitoring for LLM and agent workflows. <\/div>
Supporting Software Engineering <\/div>
• <\/div>
Expert -level proficiency in Python, RESTful API development, microservices architecture, and containerized deployments (Kubernetes, Docker). <\/div>
• <\/div>
Experience with API frameworks such as FastAPI, FastMCP, Flask, Django, and tools like Swagger/OpenAPI. <\/div>
• <\/div>
Hands -on background in data engineering, including data transformation, SQL/NoSQL databases, and event -driven architectures. <\/div>
• <\/div>
Deep understanding of DevOps and MLOps practices, including CI/CD pipelines, infrastructure -as -code, observability platforms, model/workflow monitoring, security, and automated testing. <\/div>
• <\/div>
Proven ability to collaborate with cross -functional teams, manage project timelines, and drive technical alignment in complex engineering environments. <\/div>
• <\/div>
Exceptional communication and presentation skills with the ability to convey complex AI concepts to both technical and non -technical audiences. <\/div><\/span>