AI Engineer

format:Remotecompany:Outsource

pythonoopllmprompt engineeringai agentskafkacouchbaseelasticsearchredisany one ofcouchbasedockerkubernetesawsdistributed systemsclaude code

ragvector databasesvector searchpytorchhugging facelangchainlanggraphllamaindexci/cdjenkinsgithub actionsgrafanaprometheuslangfuselangsmith

englishB2

experience6+ years

domainFintech

locationKyiv, Ukraine · Lviv, Ukraine +2

> full description

Quantum is a global technology partner delivering high-end software products that address real-world problems.

We advance emerging technologies for outside-the-box solutions. We focus on Machine Learning, Computer Vision, Deep Learning, GIS, MLOps, Blockchain, and more.

Here at Quantum, we are dedicated to creating state-of-the-art solutions that effectively address the pressing issues faced by businesses and the world. To date, our team of exceptional people has already helped many organisations globally attain technological leadership.

We constantly discover new ways to solve never-ending business challenges by adopting new technologies, even when there isn’t yet a best practice. If you share our passion for problem-solving and making an impact, join us and enjoy getting to know our wealth of experience!

About the position

Quantum is expanding the team and has a brilliant opportunity for a Senior AI Engineer. The client is a pioneering technological research company that leverages proprietary AI-based analysis and language models to provide comprehensive insights into global stocks in multiple languages. Its mission is to bridge the knowledge gap in the investment world and empower investors to become “super-investors.” Through generative AI technology integrated into brokerage platforms and financial institutions’ infrastructures, the company provides instant fundamental analyses of global stocks and enables informed investment decisions for millions of investors worldwide.

As a Senior AI Engineer, you will design, build, and maintain the LLM-powered services behind the conversational AI of a financial platform. You will work across a large system of 20+ services, turning LLMs and NLP models into reliable, scalable, production-grade software. You will take end-to-end ownership of solutions, from architecture and technical design through production delivery, deployment, and monitoring.

Must-have skills:

6+ years of hands-on software development experience, including 2+ years building LLM-powered applications in production
Deep and proven expertise in Python, OOP, and software engineering fundamentals
Hands-on experience integrating LLM APIs into production systems, including prompt engineering, structured outputs, tool use, and agent workflows
Experience with LLM evaluation and monitoring of quality, latency, and cost in production
Hands-on experience with Apache Kafka, including topic design, consumer groups, offset management, and reliability patterns
Solid experience with NoSQL databases such as Couchbase, Redis, Elasticsearch, or similar
Practical experience with Docker and deploying services on Kubernetes
Strong experience with AWS cloud services
Experience with distributed system resilience patterns such as circuit breakers, retries, rate limiting, and dead-letter queues
Strong architectural skills with the ability to design and evolve scalable, distributed systems
Proficient and heavy user of AI-assisted development tools such as Claude Code
Proven ability to independently take features from requirements to production and take end-to-end ownership
Strong collaboration and communication skills
At least Upper-Intermediate level of English (spoken and written)

Nice-to-have skills:

Hands-on experience with RAG, vector databases, and semantic search
Experience serving and optimizing NLP or Deep Learning models in production, including PyTorch or Hugging Face Transformers
Experience with LLM/AI frameworks such as LangChain, LangGraph, LlamaIndex, or similar
Domain knowledge in financial markets, fintech, or trading platforms
Experience with CI/CD pipelines such as Jenkins or GitHub Actions
Familiarity with observability tooling such as Grafana, Prometheus, and LLM tracing tools (e.g. Langfuse, LangSmith)
Application security knowledge, including OWASP Top 10, secure coding practices, secrets management, JWT/OAuth2, and protection against prompt injection

Your tasks will include:

Design and development of scalable, high-performance Python microservices with LLMs at their core
End-to-end ownership of AI-powered features, from technical design and architecture to deployment and monitoring
Integration of LLM APIs into production workflows, including prompt management, structured outputs, tool use, and agent workflows
Building reliable LLM pipelines with model routing, fallbacks, retries, caching, streaming responses, and rate-limit handling
Development and maintenance of RAG infrastructure, including document ingestion, embeddings, and vector search
Deployment and serving of BERT-based and other NLP models in production in collaboration with Data Scientists
Optimization of AI inference for latency, throughput, and cost through batching, quantization, and appropriate infrastructure choices
Building infrastructure for automated evaluation and regression testing of prompt and model changes
Implementing tracing, logging, and monitoring of LLM calls across services to track quality, latency, and cost
Design and implementation of event-driven pipelines and streaming solutions using Apache Kafka
Ensuring reliability, fault tolerance, and performance of Kafka consumers and producers
Design and optimization of NoSQL databases and data access patterns for distributed AI systems
Implementation of vector search for retrieval and semantic search use cases
Design and implementation of RESTful APIs consumed by frontends, third-party partners, and internal services
Deployment and operation of containerized services on AWS and Kubernetes
Collaboration with Data Scientists, product managers, and DevOps engineers on architecture and system design
Continuously improving production systems, infrastructure reliability, performance, and cost efficiency
Staying up to date with LLM tooling and best practices and bringing relevant technologies into production