Ai backend engineer

one is an AI‐powered financing‐access platform built to transform how SMEs secure the capital they need to grow. With a uniquely compelling product, an exceptional founding team, a vast addressable market, and strong backing, we're positioned for something big.
We're a fast‐moving startup driven by high standards, deep curiosity, and a culture that brings out the best in each of us.
Here, you won't just write code, you'll craft end‐to‐end agentic AI products, take genuine ownership, and experience the excitement of building something bold from the ground up. We're building a production LLM-driven product (with an MVP already proven) that helps organizations identify, prioritize, and write competitive grant applications. You'll help design, implement, and operate the backend systems that power the LLM, retrieval, data pipelines, and evaluation — turning research into a reliable, secure, and scalable product.
Implement retrieval (vector database, chunking, metadata, MMR) and document ingestion pipelines for large collections of grant calls, program rules, and applicant documents.
Build robust evaluation pipelines (including automated metrics, human-in-the-loop feedback, and A/B testing) to measure relevance, factuality, and success in improving grant quality/award probability.
Ensure privacy, compliance, and data governance for sensitive grant documents (PII redaction, encryption, access controls).
Collaborate with product, research, and frontend teams to translate user workflows (scoring, ranking, drafting, suggestions) into reliable APIs and event processing.
Create monitoring, alerting, and observability for model performance, data drift, latency, and error budgets.
Produce clear docs, runbooks, and onboard engineers to the LLM backend. Automate SFT/finetuning and evaluation workflows (training infra + dataset versioning).
Implement rate-limiting, request validation, caching layers, and cost controls for external LLM providers and self-hosted models.
Lead security reviews and implement access controls, secure token handling, and audit logging. Strong Python proficiency and experience building backend services (Flask/Fast API, async frameworks).
Experience with model fine-tuning workflows (Lo RA/QLo RA/SFT), dataset management, and training infra.
Cloud experience: deploying and operating services on AWS / GCP / Azure (Kubernetes, ECS, IAM, S3, Cloud SQL, etc.).
Hugging Face Transformers, PEFT/Lo RA, Open AI API (or other hosted providers), Lang Chain/Llama Index.
Strong engineering practices: testing, CI/CD, infra as code, MLOps (MLFlow), monitoring/observability (Prometheus/Grafana, Sentry, ELK/Cloud Logging). English proficiency: Bachelor's or Master's degree in Computer Science, Engineering, or related fields. Familiarity with Lang Chain, Llama Index, or similar orchestration libs and prompt engineering best practices.
Background in ML evaluation (factuality metrics, BLEU/ROUGE useful but also human eval design).
Experience with private LLM deployment (tuned LLa MA derivatives, Mistral, etc.) Experience with data privacy, GDPR, and secure handling of sensitive documents. Hybrid working, combining office presence and remote work. one means joining an early-stage startup where your work has a real, visible impact. You'll collaborate closely with the founders, move fast, take ownership, and help shape both the product and the company from the ground up.