Senior AI Software Engineer

Location: Doha, Qatar / Remote

Position Type: Full-Time

About Avey

Avey is a deep-tech company innovating AI to transform healthcare and improve lives across the globe. 

Avey is on a mission to unlock the full potential of clinical care and make every health journey delightful.

We are looking for enthusiastic, hard-working professionals who are excited to contribute to and join Avey's mission to create a solution that will have a real and positive effect on the world.

Position Overview

We're looking for a Senior AI Software Engineer to architect and own the production AI systems powering our healthcare platform, our in-house foundational model API, and a growing suite of clinical AI APIs. This is a backend-first role with deep fluency in modern AI systems. You'll be the technical bridge between AI researchers and product engineers, turning model capabilities into reliable, low-latency, compliant APIs.

Key Responsibilities

1. AI API & Platform Architecture

* Architect and own the foundational model API and downstream clinical AI APIs such as API contracts and versioning, SLAs, e2e requests lifecycle.

* Build backend services in Python and Go serving LLM, VLM, and domain-specific workloads.

* Design the abstractions, model registry, prompt management, tool/function calling, structured outputs, and guardrails that turn research artifacts into product primitives.

2. Model Serving & Inference Optimization

* Build and operate production inference on modern LLM serving runtimes (vLLM, Ray Serve, Triton, or equivalent).

* Partner with researchers to productionize new models, tuning for latency, throughput, and GPU efficiency.

* Own performance and cost of the inference layer, including autoscaling and capacity planning across GPU fleets.

3. MLOps & AI Reliability

* Partner with DevOps on MLOps pipelines for model versioning, canary rollout, A/B eval, and rollback.

* Own AI observability, token-level tracing, PHI-safe logging, quality metrics, drift, and hallucination monitoring.

* Build offline/online evaluation (semantic, clinical-accuracy, safety) and feedback loops back to research.

4. Collaboration & Technical Leadership

* Act as the primary liason between AI researchers and product engineers.

* Set engineering standards for how teams build on the AI platform; mentor on AI systems engineering.

5. Security, Compliance & Responsible AI

* Implement AI-specific controls: prompt injection defense, PHI handling, audit logging.

* Contribute to Responsible AI (model cards, safety evals, clinical validation).

* Partner with InfoSec team to ensure compliance with ISO 27001, HIPAA, NIA Qatar, and applicable healthcare AI standards.

Minimum Requirements

* 4-year STEM degree or equivalent practical experience.

* 4+ years backend software engineering; 2+ years shipping LLM/AI systems in production.

* Strong Python (FastAPI) and production Golang experience.

* Hands-on production experience with at least one modern LLM serving runtime (vLLM, Ray Serve, Triton, or equivalent).

* Strong API design for AI workloads.

* Solid distributed systems fundamentals: PostgreSQL, Redis, queues, microservices.

* Experience with atleast 1 cloud provider.

* Proven track record collaborating directly with ML/AI researchers.

Nice to Have

* Prior experience at an AI-first company or foundation model API team.

* Healthcare experience (HIS/EMR — Cerner/Epic, FHIR, clinical NLP, medical imaging).

* Experience fine-tuning or post-training LLMs.

* Deep experience with Ray, large-scale RAG systems, or agentic frameworks.

* GPU programming or performance profiling experience.

* LLM observability tooling (LangSmith, Arize, RAGAS, Phoenix).

* Startup/scale-up, prior GCC (NIA Qatar, HIPAA, GDPR), or OSS contributions to inference/serving projects.

Note:

Avey is an equal opportunity employer. We encourage candidates from all backgrounds to apply.

This job description is not exhaustive and may be subject to change based on the evolving needs of the company.