AI Application Engineer (Agentic Systems)

About Us

Whizzbridge is hiring a Mid to Senior AI Application Engineer. WhizzBridge is a technology solutions provider and a talent enabler. On one hand, it offers clients access to best of breed engineering talent and delivers their mission critical projects using the industry's best practices. On the other hand, it attracts and trains engineering talent on cutting edge technologies, programming languages and project management practices that set them up for successful professional and financial growth.

What We Offer

Paid Leaves
Medical Insurance
Paid Udemy Courses and Certifications
Career Progression Program

Design, build and ship production grade LLM applications and autonomous agents that run against real client data and real traffic.
Build multi step agent workflows using modern orchestration frameworks, including planning, tool calling, state management and error recovery.
Integrate large language model APIs across multiple providers, including OpenAI and Anthropic, and design fallback and routing logic between them.
Design and implement tool interfaces and Model Context Protocol servers that connect agents to client systems such as CRMs, ticketing systems, databases and internal APIs.
Write system prompts and structured output schemas that produce reliable, parseable results rather than plausible prose.
Build evaluation suites that measure agent performance against defined criteria, and run them continuously rather than once before launch.
Instrument every agent with tracing and observability so that failures can be diagnosed in production, not guessed at.
Optimise for cost and latency, including prompt caching, model selection per task, streaming responses and token budgeting.
Implement defences against prompt injection and unsafe tool invocation, particularly where agents act on client data.
Collaborate with client stakeholders to translate an ambiguous business workflow into a concrete agent specification.
Document architecture decisions, known limitations and operating runbooks for handover.

Job Description

Bachelor's degree in Computer Science, Software Engineering or a related field, or equivalent demonstrable experience.
Three or more years of professional software engineering experience, with at least one year building LLM powered systems that reached production.
Strong Python, including asynchronous programming. The distinction between blocking and async aware code is treated as fundamental in this role.
Hands on experience with at least one agent orchestration framework such as LangGraph, LangChain, LlamaIndex, CrewAI or AutoGen.
Practical experience with function calling, structured outputs and tool use patterns across at least one major LLM provider.
Experience building and consuming APIs, with FastAPI or an equivalent framework.
Working knowledge of Docker and deploying containerised services to a cloud target such as AWS, GCP or Azure.
Demonstrated experience with evaluation, not only development. You have measured whether an AI system works, using something more rigorous than manual spot checks.
Strong written and verbal English. This role involves direct contact with international clients.
Comfort with rapid iteration and incomplete specifications.

Requirements

Experience with Model Context Protocol and building MCP servers.
Familiarity with evaluation tooling such as Ragas, LangSmith, DeepEval or Braintrust.
Familiarity with observability tooling such as Langfuse, Phoenix, Helicone or OpenTelemetry tracing.
Experience with retrieval augmented generation and vector databases.
Experience with sandboxed code execution environments such as E2B or Modal.
Exposure to multi agent orchestration and agent to agent communication patterns.
Experience with voice or browser based agents.
Contributions to open source AI tooling.