​​

Results-driven Agentic AI Engineer specializing in the design, development, and deployment of sophisticated autonomous and semi-autonomous AI agents. Proven ability to architect complex, multi-step agentic workflows by integrating advanced Large Language Models (LLMs) with diverse tools, APIs, and data sources. Deep expertise in agent frameworks (CrewAI, AutoGen, LangChain), advanced Retrieval-Augmented Generation (RAG) techniques, multi-agent systems, and robust evaluation methodologies. Passionate about building reliable, efficient, and scalable AI solutions that bridge the gap between LLM capabilities and real-world operational challenges. Committed to responsible AI development and continuous performance optimization.

​

These contractual associate roles offer a competitive daily rate determined by the level of experience and skills the candidate possesses. 

​

​

​

Agent System Design & Architecture:

• Conceptualise, design, and architect robust, scalable, and reliable AI agent systems (single-agent and multi-agent).

• Select appropriate agent frameworks (e.g., LangChain, AutoGen, CrewAI, LlamaIndex, or custom frameworks) and foundational models based on project requirements.

• Define agent capabilities, including tool usage, memory mechanisms, planning strategies (e.g., ReAct, Chain-of-Thought), and interaction protocols.

​Development & Implementation:

• Develop, code, and test AI agent components and workflows using Python and relevant AI/ML libraries.

• Implement complex prompt engineering strategies and fine-tune LLMs/models as needed to optimize agent performance, accuracy, and specific task handling.

• Integrate agents with diverse data sources, internal/external APIs, databases, and existing software systems.

Evaluation & Optimisation:

• Design and implement comprehensive evaluation frameworks and metrics to rigorously assess agent performance, reliability, safety, and efficiency.

• Iteratively test, analyze results, and optimize agent behavior, prompts, and underlying model configurations.

• Monitor deployed agents, identify failure points or performance degradation, and implement corrective measures.

Deployment & MLOps:

• Package, deploy, and manage agentic systems in cloud environments (AWS, GCP, Azure) or on-premise infrastructure.

• Implement MLOps best practices for version control, CI/CD pipelines, monitoring, logging, and maintenance of agentic applications.

Collaboration & Research:

• Collaborate closely with product managers, data scientists, ML researchers, software engineers, and UX designers to define requirements, iterate on designs, and deliver impactful solutions.

• Stay current with state-of-the-art advancements in AI agents, LLMs, prompt engineering, RAG, and related fields, applying relevant research to practical development.

• Document designs, implementation details, evaluation results, and operational procedures.

Safety & Ethics:

• Actively consider and implement safeguards to ensure agent safety, alignment with intended goals, and mitigation of potential biases or harmful outputs.

• Adhere to responsible AI development principles and ethical guidelines.

​

​

Education:

• Bachelor's or Master's degree (PhD preferred) in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a closely related quantitative field.

Experience:

• Proven track record (typically 3-5+ years, potentially more for senior roles) in software engineering, with a strong emphasis on AI/ML application development.

• Demonstrable hands-on experience designing, building, and deploying systems utilizing Large Language Models (LLMs).

• Significant experience working with one or more prominent AI agent development frameworks (e.g., LangChain, LlamaIndex, AutoGen, Microsoft Semantic Kernel, CrewAI).

Technical Skills:

• Programming: Expert proficiency in Python and common scientific/ML libraries (NumPy, Pandas, Scikit-learn, etc.). Familiarity with other languages (e.g., Go, Rust, Java) can be a plus.

• AI/ML: Deep understanding of machine learning concepts, deep learning architectures (especially Transformers), and natural language processing (NLP). Experience with ML frameworks like PyTorch or TensorFlow.

• LLMs & Agents: Strong grasp of LLM principles, prompt engineering techniques (few-shot, zero-shot, CoT, ReAct), retrieval-augmented generation (RAG), vector databases (e.g., Pinecone, Weaviate, Chroma), and agent design patterns.

• Software Engineering: Solid understanding of software architecture, data structures, algorithms, API design (REST, gRPC), and testing methodologies.

• Cloud & MLOps: Experience with cloud platforms (AWS, Azure, or GCP) and associated AI/ML services. Familiarity with containerization (Docker), orchestration (Kubernetes), CI/CD pipelines, and monitoring tools.

Soft Skills:

• Excellent analytical and problem-solving abilities, especially when dealing with complex and ambiguous problems.

• Strong communication skills (written and verbal) to articulate technical concepts to diverse audiences.

• Collaborative mindset and ability to work effectively in cross-functional teams.

​​​

At Alpha Matica, we are staunch advocates of diversity and firmly committed to ensuring equal opportunities for employment. We strongly believe that every individual, irrespective of their sex, race, religion, ethnicity, nationality, disability, age, sexual orientation, or gender identity, deserves a level playing field. We extend a warm invitation to individuals from groups that have historically been underrepresented in the tech industry to join our team and contribute their unique talents and perspectives.

​

Please submit your CV and a link to your GitHub profile or repository if you would like to be considered for this role. Only those selected for an interview will be contacted.

careers @ alpha - matica . com

 

(No agencies please)

​