Fullstack Lead AI Engineer
Job Description
ABOUT US
\n
Incedo is a global AI, data, and digital transformation specialist that helps leading enterprises drive innovation and business growth through technology. With over 4,000 professionals across the US, Canada, Latin America, and India, Incedo combines expertise in AI, data analytics, and digital engineering to deliver impactful solutions across Banking & Payments, Telecom, Hi-Tech, Wealth Management, and Life Sciences. At Incedo, we foster a culture of innovation, collaboration, and continuous learning, empowering our people to solve complex challenges and shape the future of technology.
\n
\n
About the Role
\n
You will own the end-to-end technical build of an AI-powered platform that ingests dense technical and engineering documentation, validates it against jurisdiction- and standard-specific knowledge bases, reasons about completeness and risk, scores confidence with clear explainability, and keeps a human in the loop for review and approval. You will architect and write production code across all three layers - a responsive front end, resilient Python services, and orchestrated GenAI agents - while setting direction and raising the quality bar for a small engineering pod.
\n
This is hands-on lead work. You should be equally strong on the engineering and the domain: the solution only works when the AI genuinely understands the telecom fiber and outside-plant context it operates in.
\n
\n
Key Responsibilities
\n
- \n
- Lead the full-stack architecture and hands-on build across front end, backend, and AI layers
- Design, develop, and deploy agent-based GenAI workflows for document-heavy telecom engineering use cases
- Build responsive, intuitive web interfaces (React or similar) for technical and non-technical users
- Build scalable Python backends and integrate LLMs (Gemini, OpenAI, open-source) into production systems
- Implement RAG and enterprise retrieval over vector databases, technical documents, and structured/geospatial data
- Develop logic that validates submissions, reasons about gaps and risk, and produces explainable confidence scores
- Design human-in-the-loop review and approval flows with full audit, versioning, and traceability
- Establish agent evaluation, tracing, and guardrails for safe, reliable, auditable, and deterministic behavior
- Deploy, monitor, and optimize on cloud for performance, latency, and cost
- Set engineering standards, review code, mentor engineers, and collaborate with product, data, and partner teams on security, governance, and responsible AI
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Required Skills & Qualifications
\n
- \n
- 5+ years building and shipping production software, with strong Python development, problem-solving, and debugging skills
- Full-stack proficiency: modern front end (React / TypeScript) plus backend service development
- Hands-on Generative AI experience: LLMs, prompt engineering, and agent-based architectures
- Experience with agentic frameworks and workflow orchestration (LangGraph / LangChain, ADK, or similar)
- Hands-on cloud and managed AI platforms (GCP / Vertex AI, or AWS / Azure equivalents) - deployment, pipelines, endpoints
- Experience building RAG pipelines and working with vector databases (Pinecone, FAISS, etc.)
- Solid knowledge of REST APIs, microservices, databases, and distributed systems
- Demonstrated technical leadership: setting direction, reviewing work, and mentoring engineers
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
Agentic & GenAI Expertise (Required)
\n
- \n
- Agent core concepts & tooling: agent harnesses / frameworks (LangGraph, ADK), tool calling, and multi-step workflow orchestration
- Memory & context: short- vs. long-term memory, context-window management for long documents, and state persistence across a multi-step workflow
- Knowledge retrieval: enterprise retrieval and document search over technical manuals, requirement sets, and structured repositories
- Evaluation & guardrails: agent evaluation benchmarks, trajectory tracing, LLM-as-a-judge, and guardrails for auditable, deterministic outputs
\n
\n
\n
\n
\n
\n
Telecom Domain Knowledge (Required)
\n
- \n
- Fiber and outside-plant (OSP) engineering and deployment: network design, construction workflows, and field documentation
- Familiarity with GIS / geospatial data and common telecom and geospatial file formats
- Understanding of the engineering-to-construction lifecycle and the approvals and compliance steps along the way
- Comfort reading and reasoning about dense procedural and technical engineering documentation and drawings
\n
\n
\n
\n
\n
\n
Nice to Have
\n
- \n
- Experience with GIS platforms, CAD, or network design/inventory systems
- Exposure to telecom OSS/BSS, network assurance, or operations tooling
- Familiarity with observability and tracing for AI systems in production
- Prior work on document-intelligence, workflow-automation, or closed-loop automation products
\n
\n
\n
\n
\n