AI Backend Engineer
About the role
- Python Full Stack Developer
- Versatile in constructing AI pipelines using LangChain, LlamaIndex, and AutoRAG, with model optimization through Optuna and GridSearchCV.
- Implement Python microservices and APIs (FastAPI/Flask/Django) with clean contracts, versioning, pagination, and rate limiting.
- Build REST/GraphQL endpoints and internal SDKs to enable AI enhanced features (prompt routing, retrieval, redaction) while maintaining strict separation from model ownership.
- Implement asynchronous and event driven processing (e.g., Celery/Kafka/queues) for high throughput pipelines and background jobs.
- Integrate services with enterprise AI platforms / LLM APIs (e.g., Azure OpenAI via enterprise gateway), handling prompt orchestration, tool invocation, moderation hooks, and response validation.
- Enforce runtime guardrails: input sanitization, PII redaction, toxicity/NSFW filters, output signing, and fallbacks.
- Implement semantic retrieval and vector search via approved platforms; do not train or host custom models.
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.
